1
0
Fork 0
alistair23-linux/include/uapi/linux/swab.h

306 lines
6.8 KiB
C
Raw Normal View History

License cleanup: add SPDX license identifier to uapi header files with no license Many user space API headers are missing licensing information, which makes it hard for compliance tools to determine the correct license. By default are files without license information under the default license of the kernel, which is GPLV2. Marking them GPLV2 would exclude them from being included in non GPLV2 code, which is obviously not intended. The user space API headers fall under the syscall exception which is in the kernels COPYING file: NOTE! This copyright does *not* cover user programs that use kernel services by normal system calls - this is merely considered normal use of the kernel, and does *not* fall under the heading of "derived work". otherwise syscall usage would not be possible. Update the files which contain no license information with an SPDX license identifier. The chosen identifier is 'GPL-2.0 WITH Linux-syscall-note' which is the officially assigned identifier for the Linux syscall exception. SPDX license identifiers are a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. See the previous patch in this series for the methodology of how this patch was researched. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 08:08:43 -06:00
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _UAPI_LINUX_SWAB_H
#define _UAPI_LINUX_SWAB_H
#include <linux/types.h>
#include <linux/compiler.h>
#include <asm/bitsperlong.h>
#include <asm/swab.h>
/*
* casts are necessary for constants, because we never know how for sure
* how U/UL/ULL map to __u16, __u32, __u64. At least not in a portable way.
*/
#define ___constant_swab16(x) ((__u16)( \
(((__u16)(x) & (__u16)0x00ffU) << 8) | \
(((__u16)(x) & (__u16)0xff00U) >> 8)))
#define ___constant_swab32(x) ((__u32)( \
(((__u32)(x) & (__u32)0x000000ffUL) << 24) | \
(((__u32)(x) & (__u32)0x0000ff00UL) << 8) | \
(((__u32)(x) & (__u32)0x00ff0000UL) >> 8) | \
(((__u32)(x) & (__u32)0xff000000UL) >> 24)))
#define ___constant_swab64(x) ((__u64)( \
(((__u64)(x) & (__u64)0x00000000000000ffULL) << 56) | \
(((__u64)(x) & (__u64)0x000000000000ff00ULL) << 40) | \
(((__u64)(x) & (__u64)0x0000000000ff0000ULL) << 24) | \
(((__u64)(x) & (__u64)0x00000000ff000000ULL) << 8) | \
(((__u64)(x) & (__u64)0x000000ff00000000ULL) >> 8) | \
(((__u64)(x) & (__u64)0x0000ff0000000000ULL) >> 24) | \
(((__u64)(x) & (__u64)0x00ff000000000000ULL) >> 40) | \
(((__u64)(x) & (__u64)0xff00000000000000ULL) >> 56)))
#define ___constant_swahw32(x) ((__u32)( \
(((__u32)(x) & (__u32)0x0000ffffUL) << 16) | \
(((__u32)(x) & (__u32)0xffff0000UL) >> 16)))
#define ___constant_swahb32(x) ((__u32)( \
(((__u32)(x) & (__u32)0x00ff00ffUL) << 8) | \
(((__u32)(x) & (__u32)0xff00ff00UL) >> 8)))
/*
* Implement the following as inlines, but define the interface using
* macros to allow constant folding when possible:
* ___swab16, ___swab32, ___swab64, ___swahw32, ___swahb32
*/
static inline __attribute_const__ __u16 __fswab16(__u16 val)
{
byteswap: try to avoid __builtin_constant_p gcc bug This is another attempt to avoid a regression in wwn_to_u64() after that started using get_unaligned_be64(), which in turn ran into a bug on gcc-4.9 through 6.1. The regression got introduced due to the combination of two separate workarounds (commits e3bde9568d99: "include/linux/unaligned: force inlining of byteswap operations" and ef3fb2422ffe: "scsi: fc: use get/put_unaligned64 for wwn access") that each try to sidestep distinct problems with gcc behavior (code growth and increased stack usage). Unfortunately after both have been applied, a more serious gcc bug has been uncovered, leading to incorrect object code that discards part of a function and causes undefined behavior. As part of this problem is how __builtin_constant_p gets evaluated on an argument passed by reference into an inline function, this avoids the use of __builtin_constant_p() for all architectures that set CONFIG_ARCH_USE_BUILTIN_BSWAP. Most architectures do not set ARCH_SUPPORTS_OPTIMIZED_INLINING, which means they probably do not suffer from the problem in the qla2xxx driver, but they might still run into it elsewhere. Both of the original workarounds were only merged in the 4.6 kernel, and the bug that is fixed by this patch should only appear if both are there, so we probably don't need to backport the fix. On the other hand, it works by simplifying the code path and should not have any negative effects. [arnd@arndb.de: fix older gcc warnings] (http://lkml.kernel.org/r/12243652.bxSxEgjgfk@wuerfel) Link: https://lkml.org/lkml/headers/2016/4/12/1103 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70232 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70646 Fixes: e3bde9568d99 ("include/linux/unaligned: force inlining of byteswap operations") Fixes: ef3fb2422ffe ("scsi: fc: use get/put_unaligned64 for wwn access") Link: http://lkml.kernel.org/r/1780465.XdtPJpi8Tt@wuerfel Signed-off-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Tested-by: Josh Poimboeuf <jpoimboe@redhat.com> # on gcc-5.3 Tested-by: Quinn Tran <quinn.tran@qlogic.com> Cc: Martin Jambor <mjambor@suse.cz> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: James Bottomley <James.Bottomley@hansenpartnership.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Himanshu Madhani <himanshu.madhani@qlogic.com> Cc: Jan Hubicka <hubicka@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-05 17:22:39 -06:00
#if defined (__arch_swab16)
return __arch_swab16(val);
#else
return ___constant_swab16(val);
#endif
}
static inline __attribute_const__ __u32 __fswab32(__u32 val)
{
byteswap: try to avoid __builtin_constant_p gcc bug This is another attempt to avoid a regression in wwn_to_u64() after that started using get_unaligned_be64(), which in turn ran into a bug on gcc-4.9 through 6.1. The regression got introduced due to the combination of two separate workarounds (commits e3bde9568d99: "include/linux/unaligned: force inlining of byteswap operations" and ef3fb2422ffe: "scsi: fc: use get/put_unaligned64 for wwn access") that each try to sidestep distinct problems with gcc behavior (code growth and increased stack usage). Unfortunately after both have been applied, a more serious gcc bug has been uncovered, leading to incorrect object code that discards part of a function and causes undefined behavior. As part of this problem is how __builtin_constant_p gets evaluated on an argument passed by reference into an inline function, this avoids the use of __builtin_constant_p() for all architectures that set CONFIG_ARCH_USE_BUILTIN_BSWAP. Most architectures do not set ARCH_SUPPORTS_OPTIMIZED_INLINING, which means they probably do not suffer from the problem in the qla2xxx driver, but they might still run into it elsewhere. Both of the original workarounds were only merged in the 4.6 kernel, and the bug that is fixed by this patch should only appear if both are there, so we probably don't need to backport the fix. On the other hand, it works by simplifying the code path and should not have any negative effects. [arnd@arndb.de: fix older gcc warnings] (http://lkml.kernel.org/r/12243652.bxSxEgjgfk@wuerfel) Link: https://lkml.org/lkml/headers/2016/4/12/1103 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70232 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70646 Fixes: e3bde9568d99 ("include/linux/unaligned: force inlining of byteswap operations") Fixes: ef3fb2422ffe ("scsi: fc: use get/put_unaligned64 for wwn access") Link: http://lkml.kernel.org/r/1780465.XdtPJpi8Tt@wuerfel Signed-off-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Tested-by: Josh Poimboeuf <jpoimboe@redhat.com> # on gcc-5.3 Tested-by: Quinn Tran <quinn.tran@qlogic.com> Cc: Martin Jambor <mjambor@suse.cz> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: James Bottomley <James.Bottomley@hansenpartnership.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Himanshu Madhani <himanshu.madhani@qlogic.com> Cc: Jan Hubicka <hubicka@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-05 17:22:39 -06:00
#if defined(__arch_swab32)
return __arch_swab32(val);
#else
return ___constant_swab32(val);
#endif
}
static inline __attribute_const__ __u64 __fswab64(__u64 val)
{
byteswap: try to avoid __builtin_constant_p gcc bug This is another attempt to avoid a regression in wwn_to_u64() after that started using get_unaligned_be64(), which in turn ran into a bug on gcc-4.9 through 6.1. The regression got introduced due to the combination of two separate workarounds (commits e3bde9568d99: "include/linux/unaligned: force inlining of byteswap operations" and ef3fb2422ffe: "scsi: fc: use get/put_unaligned64 for wwn access") that each try to sidestep distinct problems with gcc behavior (code growth and increased stack usage). Unfortunately after both have been applied, a more serious gcc bug has been uncovered, leading to incorrect object code that discards part of a function and causes undefined behavior. As part of this problem is how __builtin_constant_p gets evaluated on an argument passed by reference into an inline function, this avoids the use of __builtin_constant_p() for all architectures that set CONFIG_ARCH_USE_BUILTIN_BSWAP. Most architectures do not set ARCH_SUPPORTS_OPTIMIZED_INLINING, which means they probably do not suffer from the problem in the qla2xxx driver, but they might still run into it elsewhere. Both of the original workarounds were only merged in the 4.6 kernel, and the bug that is fixed by this patch should only appear if both are there, so we probably don't need to backport the fix. On the other hand, it works by simplifying the code path and should not have any negative effects. [arnd@arndb.de: fix older gcc warnings] (http://lkml.kernel.org/r/12243652.bxSxEgjgfk@wuerfel) Link: https://lkml.org/lkml/headers/2016/4/12/1103 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70232 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70646 Fixes: e3bde9568d99 ("include/linux/unaligned: force inlining of byteswap operations") Fixes: ef3fb2422ffe ("scsi: fc: use get/put_unaligned64 for wwn access") Link: http://lkml.kernel.org/r/1780465.XdtPJpi8Tt@wuerfel Signed-off-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Tested-by: Josh Poimboeuf <jpoimboe@redhat.com> # on gcc-5.3 Tested-by: Quinn Tran <quinn.tran@qlogic.com> Cc: Martin Jambor <mjambor@suse.cz> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: James Bottomley <James.Bottomley@hansenpartnership.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Himanshu Madhani <himanshu.madhani@qlogic.com> Cc: Jan Hubicka <hubicka@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-05 17:22:39 -06:00
#if defined (__arch_swab64)
return __arch_swab64(val);
#elif defined(__SWAB_64_THRU_32__)
__u32 h = val >> 32;
__u32 l = val & ((1ULL << 32) - 1);
return (((__u64)__fswab32(l)) << 32) | ((__u64)(__fswab32(h)));
#else
return ___constant_swab64(val);
#endif
}
static inline __attribute_const__ __u32 __fswahw32(__u32 val)
{
#ifdef __arch_swahw32
return __arch_swahw32(val);
#else
return ___constant_swahw32(val);
#endif
}
static inline __attribute_const__ __u32 __fswahb32(__u32 val)
{
#ifdef __arch_swahb32
return __arch_swahb32(val);
#else
return ___constant_swahb32(val);
#endif
}
/**
* __swab16 - return a byteswapped 16-bit value
* @x: value to byteswap
*/
byteswap: try to avoid __builtin_constant_p gcc bug This is another attempt to avoid a regression in wwn_to_u64() after that started using get_unaligned_be64(), which in turn ran into a bug on gcc-4.9 through 6.1. The regression got introduced due to the combination of two separate workarounds (commits e3bde9568d99: "include/linux/unaligned: force inlining of byteswap operations" and ef3fb2422ffe: "scsi: fc: use get/put_unaligned64 for wwn access") that each try to sidestep distinct problems with gcc behavior (code growth and increased stack usage). Unfortunately after both have been applied, a more serious gcc bug has been uncovered, leading to incorrect object code that discards part of a function and causes undefined behavior. As part of this problem is how __builtin_constant_p gets evaluated on an argument passed by reference into an inline function, this avoids the use of __builtin_constant_p() for all architectures that set CONFIG_ARCH_USE_BUILTIN_BSWAP. Most architectures do not set ARCH_SUPPORTS_OPTIMIZED_INLINING, which means they probably do not suffer from the problem in the qla2xxx driver, but they might still run into it elsewhere. Both of the original workarounds were only merged in the 4.6 kernel, and the bug that is fixed by this patch should only appear if both are there, so we probably don't need to backport the fix. On the other hand, it works by simplifying the code path and should not have any negative effects. [arnd@arndb.de: fix older gcc warnings] (http://lkml.kernel.org/r/12243652.bxSxEgjgfk@wuerfel) Link: https://lkml.org/lkml/headers/2016/4/12/1103 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70232 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70646 Fixes: e3bde9568d99 ("include/linux/unaligned: force inlining of byteswap operations") Fixes: ef3fb2422ffe ("scsi: fc: use get/put_unaligned64 for wwn access") Link: http://lkml.kernel.org/r/1780465.XdtPJpi8Tt@wuerfel Signed-off-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Tested-by: Josh Poimboeuf <jpoimboe@redhat.com> # on gcc-5.3 Tested-by: Quinn Tran <quinn.tran@qlogic.com> Cc: Martin Jambor <mjambor@suse.cz> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: James Bottomley <James.Bottomley@hansenpartnership.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Himanshu Madhani <himanshu.madhani@qlogic.com> Cc: Jan Hubicka <hubicka@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-05 17:22:39 -06:00
#ifdef __HAVE_BUILTIN_BSWAP16__
#define __swab16(x) (__u16)__builtin_bswap16((__u16)(x))
#else
#define __swab16(x) \
(__builtin_constant_p((__u16)(x)) ? \
___constant_swab16(x) : \
__fswab16(x))
byteswap: try to avoid __builtin_constant_p gcc bug This is another attempt to avoid a regression in wwn_to_u64() after that started using get_unaligned_be64(), which in turn ran into a bug on gcc-4.9 through 6.1. The regression got introduced due to the combination of two separate workarounds (commits e3bde9568d99: "include/linux/unaligned: force inlining of byteswap operations" and ef3fb2422ffe: "scsi: fc: use get/put_unaligned64 for wwn access") that each try to sidestep distinct problems with gcc behavior (code growth and increased stack usage). Unfortunately after both have been applied, a more serious gcc bug has been uncovered, leading to incorrect object code that discards part of a function and causes undefined behavior. As part of this problem is how __builtin_constant_p gets evaluated on an argument passed by reference into an inline function, this avoids the use of __builtin_constant_p() for all architectures that set CONFIG_ARCH_USE_BUILTIN_BSWAP. Most architectures do not set ARCH_SUPPORTS_OPTIMIZED_INLINING, which means they probably do not suffer from the problem in the qla2xxx driver, but they might still run into it elsewhere. Both of the original workarounds were only merged in the 4.6 kernel, and the bug that is fixed by this patch should only appear if both are there, so we probably don't need to backport the fix. On the other hand, it works by simplifying the code path and should not have any negative effects. [arnd@arndb.de: fix older gcc warnings] (http://lkml.kernel.org/r/12243652.bxSxEgjgfk@wuerfel) Link: https://lkml.org/lkml/headers/2016/4/12/1103 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70232 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70646 Fixes: e3bde9568d99 ("include/linux/unaligned: force inlining of byteswap operations") Fixes: ef3fb2422ffe ("scsi: fc: use get/put_unaligned64 for wwn access") Link: http://lkml.kernel.org/r/1780465.XdtPJpi8Tt@wuerfel Signed-off-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Tested-by: Josh Poimboeuf <jpoimboe@redhat.com> # on gcc-5.3 Tested-by: Quinn Tran <quinn.tran@qlogic.com> Cc: Martin Jambor <mjambor@suse.cz> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: James Bottomley <James.Bottomley@hansenpartnership.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Himanshu Madhani <himanshu.madhani@qlogic.com> Cc: Jan Hubicka <hubicka@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-05 17:22:39 -06:00
#endif
/**
* __swab32 - return a byteswapped 32-bit value
* @x: value to byteswap
*/
byteswap: try to avoid __builtin_constant_p gcc bug This is another attempt to avoid a regression in wwn_to_u64() after that started using get_unaligned_be64(), which in turn ran into a bug on gcc-4.9 through 6.1. The regression got introduced due to the combination of two separate workarounds (commits e3bde9568d99: "include/linux/unaligned: force inlining of byteswap operations" and ef3fb2422ffe: "scsi: fc: use get/put_unaligned64 for wwn access") that each try to sidestep distinct problems with gcc behavior (code growth and increased stack usage). Unfortunately after both have been applied, a more serious gcc bug has been uncovered, leading to incorrect object code that discards part of a function and causes undefined behavior. As part of this problem is how __builtin_constant_p gets evaluated on an argument passed by reference into an inline function, this avoids the use of __builtin_constant_p() for all architectures that set CONFIG_ARCH_USE_BUILTIN_BSWAP. Most architectures do not set ARCH_SUPPORTS_OPTIMIZED_INLINING, which means they probably do not suffer from the problem in the qla2xxx driver, but they might still run into it elsewhere. Both of the original workarounds were only merged in the 4.6 kernel, and the bug that is fixed by this patch should only appear if both are there, so we probably don't need to backport the fix. On the other hand, it works by simplifying the code path and should not have any negative effects. [arnd@arndb.de: fix older gcc warnings] (http://lkml.kernel.org/r/12243652.bxSxEgjgfk@wuerfel) Link: https://lkml.org/lkml/headers/2016/4/12/1103 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70232 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70646 Fixes: e3bde9568d99 ("include/linux/unaligned: force inlining of byteswap operations") Fixes: ef3fb2422ffe ("scsi: fc: use get/put_unaligned64 for wwn access") Link: http://lkml.kernel.org/r/1780465.XdtPJpi8Tt@wuerfel Signed-off-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Tested-by: Josh Poimboeuf <jpoimboe@redhat.com> # on gcc-5.3 Tested-by: Quinn Tran <quinn.tran@qlogic.com> Cc: Martin Jambor <mjambor@suse.cz> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: James Bottomley <James.Bottomley@hansenpartnership.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Himanshu Madhani <himanshu.madhani@qlogic.com> Cc: Jan Hubicka <hubicka@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-05 17:22:39 -06:00
#ifdef __HAVE_BUILTIN_BSWAP32__
#define __swab32(x) (__u32)__builtin_bswap32((__u32)(x))
#else
#define __swab32(x) \
(__builtin_constant_p((__u32)(x)) ? \
___constant_swab32(x) : \
__fswab32(x))
byteswap: try to avoid __builtin_constant_p gcc bug This is another attempt to avoid a regression in wwn_to_u64() after that started using get_unaligned_be64(), which in turn ran into a bug on gcc-4.9 through 6.1. The regression got introduced due to the combination of two separate workarounds (commits e3bde9568d99: "include/linux/unaligned: force inlining of byteswap operations" and ef3fb2422ffe: "scsi: fc: use get/put_unaligned64 for wwn access") that each try to sidestep distinct problems with gcc behavior (code growth and increased stack usage). Unfortunately after both have been applied, a more serious gcc bug has been uncovered, leading to incorrect object code that discards part of a function and causes undefined behavior. As part of this problem is how __builtin_constant_p gets evaluated on an argument passed by reference into an inline function, this avoids the use of __builtin_constant_p() for all architectures that set CONFIG_ARCH_USE_BUILTIN_BSWAP. Most architectures do not set ARCH_SUPPORTS_OPTIMIZED_INLINING, which means they probably do not suffer from the problem in the qla2xxx driver, but they might still run into it elsewhere. Both of the original workarounds were only merged in the 4.6 kernel, and the bug that is fixed by this patch should only appear if both are there, so we probably don't need to backport the fix. On the other hand, it works by simplifying the code path and should not have any negative effects. [arnd@arndb.de: fix older gcc warnings] (http://lkml.kernel.org/r/12243652.bxSxEgjgfk@wuerfel) Link: https://lkml.org/lkml/headers/2016/4/12/1103 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70232 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70646 Fixes: e3bde9568d99 ("include/linux/unaligned: force inlining of byteswap operations") Fixes: ef3fb2422ffe ("scsi: fc: use get/put_unaligned64 for wwn access") Link: http://lkml.kernel.org/r/1780465.XdtPJpi8Tt@wuerfel Signed-off-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Tested-by: Josh Poimboeuf <jpoimboe@redhat.com> # on gcc-5.3 Tested-by: Quinn Tran <quinn.tran@qlogic.com> Cc: Martin Jambor <mjambor@suse.cz> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: James Bottomley <James.Bottomley@hansenpartnership.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Himanshu Madhani <himanshu.madhani@qlogic.com> Cc: Jan Hubicka <hubicka@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-05 17:22:39 -06:00
#endif
/**
* __swab64 - return a byteswapped 64-bit value
* @x: value to byteswap
*/
byteswap: try to avoid __builtin_constant_p gcc bug This is another attempt to avoid a regression in wwn_to_u64() after that started using get_unaligned_be64(), which in turn ran into a bug on gcc-4.9 through 6.1. The regression got introduced due to the combination of two separate workarounds (commits e3bde9568d99: "include/linux/unaligned: force inlining of byteswap operations" and ef3fb2422ffe: "scsi: fc: use get/put_unaligned64 for wwn access") that each try to sidestep distinct problems with gcc behavior (code growth and increased stack usage). Unfortunately after both have been applied, a more serious gcc bug has been uncovered, leading to incorrect object code that discards part of a function and causes undefined behavior. As part of this problem is how __builtin_constant_p gets evaluated on an argument passed by reference into an inline function, this avoids the use of __builtin_constant_p() for all architectures that set CONFIG_ARCH_USE_BUILTIN_BSWAP. Most architectures do not set ARCH_SUPPORTS_OPTIMIZED_INLINING, which means they probably do not suffer from the problem in the qla2xxx driver, but they might still run into it elsewhere. Both of the original workarounds were only merged in the 4.6 kernel, and the bug that is fixed by this patch should only appear if both are there, so we probably don't need to backport the fix. On the other hand, it works by simplifying the code path and should not have any negative effects. [arnd@arndb.de: fix older gcc warnings] (http://lkml.kernel.org/r/12243652.bxSxEgjgfk@wuerfel) Link: https://lkml.org/lkml/headers/2016/4/12/1103 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70232 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70646 Fixes: e3bde9568d99 ("include/linux/unaligned: force inlining of byteswap operations") Fixes: ef3fb2422ffe ("scsi: fc: use get/put_unaligned64 for wwn access") Link: http://lkml.kernel.org/r/1780465.XdtPJpi8Tt@wuerfel Signed-off-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Tested-by: Josh Poimboeuf <jpoimboe@redhat.com> # on gcc-5.3 Tested-by: Quinn Tran <quinn.tran@qlogic.com> Cc: Martin Jambor <mjambor@suse.cz> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: James Bottomley <James.Bottomley@hansenpartnership.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Himanshu Madhani <himanshu.madhani@qlogic.com> Cc: Jan Hubicka <hubicka@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-05 17:22:39 -06:00
#ifdef __HAVE_BUILTIN_BSWAP64__
#define __swab64(x) (__u64)__builtin_bswap64((__u64)(x))
#else
#define __swab64(x) \
(__builtin_constant_p((__u64)(x)) ? \
___constant_swab64(x) : \
__fswab64(x))
byteswap: try to avoid __builtin_constant_p gcc bug This is another attempt to avoid a regression in wwn_to_u64() after that started using get_unaligned_be64(), which in turn ran into a bug on gcc-4.9 through 6.1. The regression got introduced due to the combination of two separate workarounds (commits e3bde9568d99: "include/linux/unaligned: force inlining of byteswap operations" and ef3fb2422ffe: "scsi: fc: use get/put_unaligned64 for wwn access") that each try to sidestep distinct problems with gcc behavior (code growth and increased stack usage). Unfortunately after both have been applied, a more serious gcc bug has been uncovered, leading to incorrect object code that discards part of a function and causes undefined behavior. As part of this problem is how __builtin_constant_p gets evaluated on an argument passed by reference into an inline function, this avoids the use of __builtin_constant_p() for all architectures that set CONFIG_ARCH_USE_BUILTIN_BSWAP. Most architectures do not set ARCH_SUPPORTS_OPTIMIZED_INLINING, which means they probably do not suffer from the problem in the qla2xxx driver, but they might still run into it elsewhere. Both of the original workarounds were only merged in the 4.6 kernel, and the bug that is fixed by this patch should only appear if both are there, so we probably don't need to backport the fix. On the other hand, it works by simplifying the code path and should not have any negative effects. [arnd@arndb.de: fix older gcc warnings] (http://lkml.kernel.org/r/12243652.bxSxEgjgfk@wuerfel) Link: https://lkml.org/lkml/headers/2016/4/12/1103 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70232 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70646 Fixes: e3bde9568d99 ("include/linux/unaligned: force inlining of byteswap operations") Fixes: ef3fb2422ffe ("scsi: fc: use get/put_unaligned64 for wwn access") Link: http://lkml.kernel.org/r/1780465.XdtPJpi8Tt@wuerfel Signed-off-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Tested-by: Josh Poimboeuf <jpoimboe@redhat.com> # on gcc-5.3 Tested-by: Quinn Tran <quinn.tran@qlogic.com> Cc: Martin Jambor <mjambor@suse.cz> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: James Bottomley <James.Bottomley@hansenpartnership.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Thomas Graf <tgraf@suug.ch> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Himanshu Madhani <himanshu.madhani@qlogic.com> Cc: Jan Hubicka <hubicka@ucw.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-05 17:22:39 -06:00
#endif
static __always_inline unsigned long __swab(const unsigned long y)
{
#if BITS_PER_LONG == 64
return __swab64(y);
#else /* BITS_PER_LONG == 32 */
return __swab32(y);
#endif
}
/**
* __swahw32 - return a word-swapped 32-bit value
* @x: value to wordswap
*
* __swahw32(0x12340000) is 0x00001234
*/
#define __swahw32(x) \
(__builtin_constant_p((__u32)(x)) ? \
___constant_swahw32(x) : \
__fswahw32(x))
/**
* __swahb32 - return a high and low byte-swapped 32-bit value
* @x: value to byteswap
*
* __swahb32(0x12345678) is 0x34127856
*/
#define __swahb32(x) \
(__builtin_constant_p((__u32)(x)) ? \
___constant_swahb32(x) : \
__fswahb32(x))
/**
* __swab16p - return a byteswapped 16-bit value from a pointer
* @p: pointer to a naturally-aligned 16-bit value
*/
include/uapi/linux/byteorder, swab: force inlining of some byteswap operations Sometimes gcc mysteriously doesn't inline very small functions we expect to be inlined. See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 With this .config: http://busybox.net/~vda/kernel_config_OPTIMIZE_INLINING_and_Os, the following functions get deinlined many times. Examples of disassembly: <get_unaligned_be16> (12 copies, 51 calls): 66 8b 07 mov (%rdi),%ax 55 push %rbp 48 89 e5 mov %rsp,%rbp 86 e0 xchg %ah,%al 5d pop %rbp c3 retq <get_unaligned_be32> (12 copies, 135 calls): 8b 07 mov (%rdi),%eax 55 push %rbp 48 89 e5 mov %rsp,%rbp 0f c8 bswap %eax 5d pop %rbp c3 retq <get_unaligned_be64> (2 copies, 20 calls): 48 8b 07 mov (%rdi),%rax 55 push %rbp 48 89 e5 mov %rsp,%rbp 48 0f c8 bswap %rax 5d pop %rbp c3 retq <__swab16p> (16 copies, 146 calls): 55 push %rbp 89 f8 mov %edi,%eax 86 e0 xchg %ah,%al 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq <__swab32p> (43 copies, ~560 calls): 55 push %rbp 89 f8 mov %edi,%eax 0f c8 bswap %eax 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq <__swab64p> (21 copies, 119 calls): 55 push %rbp 48 89 f8 mov %rdi,%rax 48 0f c8 bswap %rax 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq <__swab32s> (6 copies, 47 calls): 8b 07 mov (%rdi),%eax 55 push %rbp 48 89 e5 mov %rsp,%rbp 0f c8 bswap %eax 89 07 mov %eax,(%rdi) 5d pop %rbp c3 retq This patch fixes this via s/inline/__always_inline/. Code size decrease after the patch is ~4.5k: text data bss dec hex filename 92202377 20826112 36417536 149446025 8e85d89 vmlinux 92197848 20826112 36417536 149441496 8e84bd8 vmlinux5_swap_after Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Thomas Graf <tgraf@suug.ch> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-17 15:22:44 -06:00
static __always_inline __u16 __swab16p(const __u16 *p)
{
#ifdef __arch_swab16p
return __arch_swab16p(p);
#else
return __swab16(*p);
#endif
}
/**
* __swab32p - return a byteswapped 32-bit value from a pointer
* @p: pointer to a naturally-aligned 32-bit value
*/
include/uapi/linux/byteorder, swab: force inlining of some byteswap operations Sometimes gcc mysteriously doesn't inline very small functions we expect to be inlined. See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 With this .config: http://busybox.net/~vda/kernel_config_OPTIMIZE_INLINING_and_Os, the following functions get deinlined many times. Examples of disassembly: <get_unaligned_be16> (12 copies, 51 calls): 66 8b 07 mov (%rdi),%ax 55 push %rbp 48 89 e5 mov %rsp,%rbp 86 e0 xchg %ah,%al 5d pop %rbp c3 retq <get_unaligned_be32> (12 copies, 135 calls): 8b 07 mov (%rdi),%eax 55 push %rbp 48 89 e5 mov %rsp,%rbp 0f c8 bswap %eax 5d pop %rbp c3 retq <get_unaligned_be64> (2 copies, 20 calls): 48 8b 07 mov (%rdi),%rax 55 push %rbp 48 89 e5 mov %rsp,%rbp 48 0f c8 bswap %rax 5d pop %rbp c3 retq <__swab16p> (16 copies, 146 calls): 55 push %rbp 89 f8 mov %edi,%eax 86 e0 xchg %ah,%al 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq <__swab32p> (43 copies, ~560 calls): 55 push %rbp 89 f8 mov %edi,%eax 0f c8 bswap %eax 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq <__swab64p> (21 copies, 119 calls): 55 push %rbp 48 89 f8 mov %rdi,%rax 48 0f c8 bswap %rax 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq <__swab32s> (6 copies, 47 calls): 8b 07 mov (%rdi),%eax 55 push %rbp 48 89 e5 mov %rsp,%rbp 0f c8 bswap %eax 89 07 mov %eax,(%rdi) 5d pop %rbp c3 retq This patch fixes this via s/inline/__always_inline/. Code size decrease after the patch is ~4.5k: text data bss dec hex filename 92202377 20826112 36417536 149446025 8e85d89 vmlinux 92197848 20826112 36417536 149441496 8e84bd8 vmlinux5_swap_after Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Thomas Graf <tgraf@suug.ch> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-17 15:22:44 -06:00
static __always_inline __u32 __swab32p(const __u32 *p)
{
#ifdef __arch_swab32p
return __arch_swab32p(p);
#else
return __swab32(*p);
#endif
}
/**
* __swab64p - return a byteswapped 64-bit value from a pointer
* @p: pointer to a naturally-aligned 64-bit value
*/
include/uapi/linux/byteorder, swab: force inlining of some byteswap operations Sometimes gcc mysteriously doesn't inline very small functions we expect to be inlined. See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 With this .config: http://busybox.net/~vda/kernel_config_OPTIMIZE_INLINING_and_Os, the following functions get deinlined many times. Examples of disassembly: <get_unaligned_be16> (12 copies, 51 calls): 66 8b 07 mov (%rdi),%ax 55 push %rbp 48 89 e5 mov %rsp,%rbp 86 e0 xchg %ah,%al 5d pop %rbp c3 retq <get_unaligned_be32> (12 copies, 135 calls): 8b 07 mov (%rdi),%eax 55 push %rbp 48 89 e5 mov %rsp,%rbp 0f c8 bswap %eax 5d pop %rbp c3 retq <get_unaligned_be64> (2 copies, 20 calls): 48 8b 07 mov (%rdi),%rax 55 push %rbp 48 89 e5 mov %rsp,%rbp 48 0f c8 bswap %rax 5d pop %rbp c3 retq <__swab16p> (16 copies, 146 calls): 55 push %rbp 89 f8 mov %edi,%eax 86 e0 xchg %ah,%al 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq <__swab32p> (43 copies, ~560 calls): 55 push %rbp 89 f8 mov %edi,%eax 0f c8 bswap %eax 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq <__swab64p> (21 copies, 119 calls): 55 push %rbp 48 89 f8 mov %rdi,%rax 48 0f c8 bswap %rax 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq <__swab32s> (6 copies, 47 calls): 8b 07 mov (%rdi),%eax 55 push %rbp 48 89 e5 mov %rsp,%rbp 0f c8 bswap %eax 89 07 mov %eax,(%rdi) 5d pop %rbp c3 retq This patch fixes this via s/inline/__always_inline/. Code size decrease after the patch is ~4.5k: text data bss dec hex filename 92202377 20826112 36417536 149446025 8e85d89 vmlinux 92197848 20826112 36417536 149441496 8e84bd8 vmlinux5_swap_after Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Thomas Graf <tgraf@suug.ch> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-17 15:22:44 -06:00
static __always_inline __u64 __swab64p(const __u64 *p)
{
#ifdef __arch_swab64p
return __arch_swab64p(p);
#else
return __swab64(*p);
#endif
}
/**
* __swahw32p - return a wordswapped 32-bit value from a pointer
* @p: pointer to a naturally-aligned 32-bit value
*
* See __swahw32() for details of wordswapping.
*/
static inline __u32 __swahw32p(const __u32 *p)
{
#ifdef __arch_swahw32p
return __arch_swahw32p(p);
#else
return __swahw32(*p);
#endif
}
/**
* __swahb32p - return a high and low byteswapped 32-bit value from a pointer
* @p: pointer to a naturally-aligned 32-bit value
*
* See __swahb32() for details of high/low byteswapping.
*/
static inline __u32 __swahb32p(const __u32 *p)
{
#ifdef __arch_swahb32p
return __arch_swahb32p(p);
#else
return __swahb32(*p);
#endif
}
/**
* __swab16s - byteswap a 16-bit value in-place
* @p: pointer to a naturally-aligned 16-bit value
*/
static inline void __swab16s(__u16 *p)
{
#ifdef __arch_swab16s
__arch_swab16s(p);
#else
*p = __swab16p(p);
#endif
}
/**
* __swab32s - byteswap a 32-bit value in-place
* @p: pointer to a naturally-aligned 32-bit value
*/
include/uapi/linux/byteorder, swab: force inlining of some byteswap operations Sometimes gcc mysteriously doesn't inline very small functions we expect to be inlined. See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 With this .config: http://busybox.net/~vda/kernel_config_OPTIMIZE_INLINING_and_Os, the following functions get deinlined many times. Examples of disassembly: <get_unaligned_be16> (12 copies, 51 calls): 66 8b 07 mov (%rdi),%ax 55 push %rbp 48 89 e5 mov %rsp,%rbp 86 e0 xchg %ah,%al 5d pop %rbp c3 retq <get_unaligned_be32> (12 copies, 135 calls): 8b 07 mov (%rdi),%eax 55 push %rbp 48 89 e5 mov %rsp,%rbp 0f c8 bswap %eax 5d pop %rbp c3 retq <get_unaligned_be64> (2 copies, 20 calls): 48 8b 07 mov (%rdi),%rax 55 push %rbp 48 89 e5 mov %rsp,%rbp 48 0f c8 bswap %rax 5d pop %rbp c3 retq <__swab16p> (16 copies, 146 calls): 55 push %rbp 89 f8 mov %edi,%eax 86 e0 xchg %ah,%al 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq <__swab32p> (43 copies, ~560 calls): 55 push %rbp 89 f8 mov %edi,%eax 0f c8 bswap %eax 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq <__swab64p> (21 copies, 119 calls): 55 push %rbp 48 89 f8 mov %rdi,%rax 48 0f c8 bswap %rax 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq <__swab32s> (6 copies, 47 calls): 8b 07 mov (%rdi),%eax 55 push %rbp 48 89 e5 mov %rsp,%rbp 0f c8 bswap %eax 89 07 mov %eax,(%rdi) 5d pop %rbp c3 retq This patch fixes this via s/inline/__always_inline/. Code size decrease after the patch is ~4.5k: text data bss dec hex filename 92202377 20826112 36417536 149446025 8e85d89 vmlinux 92197848 20826112 36417536 149441496 8e84bd8 vmlinux5_swap_after Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Thomas Graf <tgraf@suug.ch> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-17 15:22:44 -06:00
static __always_inline void __swab32s(__u32 *p)
{
#ifdef __arch_swab32s
__arch_swab32s(p);
#else
*p = __swab32p(p);
#endif
}
/**
* __swab64s - byteswap a 64-bit value in-place
* @p: pointer to a naturally-aligned 64-bit value
*/
include/uapi/linux/byteorder, swab: force inlining of some byteswap operations Sometimes gcc mysteriously doesn't inline very small functions we expect to be inlined. See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122 With this .config: http://busybox.net/~vda/kernel_config_OPTIMIZE_INLINING_and_Os, the following functions get deinlined many times. Examples of disassembly: <get_unaligned_be16> (12 copies, 51 calls): 66 8b 07 mov (%rdi),%ax 55 push %rbp 48 89 e5 mov %rsp,%rbp 86 e0 xchg %ah,%al 5d pop %rbp c3 retq <get_unaligned_be32> (12 copies, 135 calls): 8b 07 mov (%rdi),%eax 55 push %rbp 48 89 e5 mov %rsp,%rbp 0f c8 bswap %eax 5d pop %rbp c3 retq <get_unaligned_be64> (2 copies, 20 calls): 48 8b 07 mov (%rdi),%rax 55 push %rbp 48 89 e5 mov %rsp,%rbp 48 0f c8 bswap %rax 5d pop %rbp c3 retq <__swab16p> (16 copies, 146 calls): 55 push %rbp 89 f8 mov %edi,%eax 86 e0 xchg %ah,%al 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq <__swab32p> (43 copies, ~560 calls): 55 push %rbp 89 f8 mov %edi,%eax 0f c8 bswap %eax 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq <__swab64p> (21 copies, 119 calls): 55 push %rbp 48 89 f8 mov %rdi,%rax 48 0f c8 bswap %rax 48 89 e5 mov %rsp,%rbp 5d pop %rbp c3 retq <__swab32s> (6 copies, 47 calls): 8b 07 mov (%rdi),%eax 55 push %rbp 48 89 e5 mov %rsp,%rbp 0f c8 bswap %eax 89 07 mov %eax,(%rdi) 5d pop %rbp c3 retq This patch fixes this via s/inline/__always_inline/. Code size decrease after the patch is ~4.5k: text data bss dec hex filename 92202377 20826112 36417536 149446025 8e85d89 vmlinux 92197848 20826112 36417536 149441496 8e84bd8 vmlinux5_swap_after Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Thomas Graf <tgraf@suug.ch> Cc: Peter Zijlstra <peterz@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-17 15:22:44 -06:00
static __always_inline void __swab64s(__u64 *p)
{
#ifdef __arch_swab64s
__arch_swab64s(p);
#else
*p = __swab64p(p);
#endif
}
/**
* __swahw32s - wordswap a 32-bit value in-place
* @p: pointer to a naturally-aligned 32-bit value
*
* See __swahw32() for details of wordswapping
*/
static inline void __swahw32s(__u32 *p)
{
#ifdef __arch_swahw32s
__arch_swahw32s(p);
#else
*p = __swahw32p(p);
#endif
}
/**
* __swahb32s - high and low byteswap a 32-bit value in-place
* @p: pointer to a naturally-aligned 32-bit value
*
* See __swahb32() for details of high and low byte swapping
*/
static inline void __swahb32s(__u32 *p)
{
#ifdef __arch_swahb32s
__arch_swahb32s(p);
#else
*p = __swahb32p(p);
#endif
}
#endif /* _UAPI_LINUX_SWAB_H */